Lianghua He

6

Papers

48

Total Citations

Papers (6)

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer

M²RL-Net: Multi-View and Multi-Level Relation Learning Network for Weakly-Supervised Image Forgery Detection

CoSMIC: Continual Self-supervised Learning for Multi-Domain Medical Imaging via Conditional Mutual Information Maximization

AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images

MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection